Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    behind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phan
    -0.07
    !!.
    -0.07
     dedim
    -0.07
    pm
    -0.06
    -color
    -0.06
    dato
    -0.06
    FH
    -0.06
     поч
    -0.06
     pharmacy
    -0.06
     başv
    -0.06
    POSITIVE LOGITS
    .Mult
    0.06
     Shotgun
    0.06
    Sil
    0.06
    (tile
    0.06
    :true
    0.06
     reflex
    0.06
    (Thread
    0.06
    close
    0.06
    Fact
    0.06
     Glide
    0.06
    Act Density 0.021%

    No Known Activations